维基百科上的小众编辑如何悄然重塑大模型价值观，揭示训练数据背后的隐形影响力
arXiv:2606.24890v1 Announce Type: cross Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikiped…
量化数据影响与相似性的一致性，为理解大模型行为提供全新分析视角。
arXiv:2606.23591v1 Announce Type: new Abstract: One way to understand LLM behavior is to trace its output back to the training data. Two types of meas…
元评估揭示哪些因素真正决定表格大模型性能，模型架构vs训练数据的深度对比。
arXiv:2501.14717v2 Announce Type: replace Abstract: Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight …
提出“数据探针”新范式，从因果层面揭示数据如何影响大模型性能，AI研究必读。
arXiv:2605.18801v1 Announce Type: cross Abstract: Data is fundamental to large language models (LLMs). However, understanding of what makes certain da…